I’m trying to create an Assistant with a Vector database. I’ve set everything up, but now I’m being blocked from even testing it because the one request exceeds the 30,000 TPM rate limit on 4o.
I can literally do this on my own CustomGPT with no issues.
Why on Earth am I being blocked on a COMMERCIAL product that I’m trying to give OpenAI money for?
If I can’t even test it, how am I meant to deploy this?
Apparently I have to spend more to increase the limit, but the whole point is to USE it to spend more!
2 Likes
Looks like you are Tier 1. If you pay $50 and it’s been at least 7 days, you will go to Tier 2 which has a 450,000 TPM on 4o.
Why the limits?
Why do we have rate limits?
Rate limits are a common practice for APIs, and they’re put in place for a few different reasons:
- They help protect against abuse or misuse of the API. For example, a malicious actor could flood the API with requests in an attempt to overload it or cause disruptions in service. By setting rate limits, OpenAI can prevent this kind of activity.
- Rate limits help ensure that everyone has fair access to the API. If one person or organization makes an excessive number of requests, it could bog down the API for everyone else. By throttling the number of requests that a single user can make, OpenAI ensures that the most number of people have an opportunity to use the API without experiencing slowdowns.
- Rate limits can help OpenAI manage the aggregate load on its infrastructure. If requests to the API increase dramatically, it could tax the servers and cause performance issues. By setting rate limits, OpenAI can help maintain a smooth and consistent experience for all users.
6 Likes
Do you mean if I add $50 in credit to the account? Or I actually spend $50 in API credit?
Here is the rule for T2:
$50 paid and 7+ days since first successful payment
So, from payment, not burn/spend.
So if you’ve had the API for at least 7 days, and drop a cumulative $50, you are at T2.
3 Likes